Model

GPT-4 32K 0314

OpenAI · closed weights

openai.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
HellaSwag95.3overall_accuracyN/AIndependentmediumarxiv.org
WinoGrande87.5accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…